MetaCues: Enabling Critical Engagement with Generative AI for Information Seeking and Sensemaking

2026-03-20

AI Summary

This work addresses the tendency of generative AI search tools to induce cognitive offloading, which often leads users to passively accept information, exhibit selective attention, and engage in homogeneous exploration, thereby undermining critical thinking. To counteract this, the paper introduces MetaCues—the first interactive system that integrates metacognitive prompting directly into the generative AI search process. By dynamically displaying prompts and a note-taking interface alongside AI responses, MetaCues encourages users to actively formulate queries, verify results, and explore topics from multiple perspectives. In an online experiment with 146 participants, MetaCues significantly increased users’ judgment confidence compared to a no-prompt baseline and fostered broader exploratory behavior on low-controversy, low-familiarity topics, effectively enhancing metacognitive engagement and critical thinking during information seeking.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Humans and AI: Intelligent User Interfaces

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Generative AI (GenAI) search tools are increasingly used for information seeking, yet their design tends to encourage cognitive offloading, which may lead to passive engagement, selective attention, and informational homogenization. Effective use requires metacognitive engagement to craft good prompts, verify AI outputs, and critically engage with information. We developed MetaCues, a novel GenAI-based interactive tool for information seeking that delivers metacognitive cues alongside AI responses and a note-taking interface to guide users' search and associated learning. Through an online study (N = 146), we compared MetaCues to a baseline tool without cues, across two broad search topics that required participants to explore diverse perspectives in order to make informed judgments. Preliminary findings regarding participants' search behavior show that MetaCues leads to increased confidence in attitudinal judgments about the search topic as well as broader inquiry, with the latter effect emerging primarily for the topic that was less controversial and with which participants had relatively less familiarity. Accordingly, we outline directions for future qualitative exploration of search interactions and inquiry patterns.

Problem

• Generative AI
• information seeking
• cognitive offloading
• metacognitive engagement
• informational homogenization

Innovation

• metacognitive cues
• generative AI
• information seeking
• critical engagement
• sensemaking